What Guides the Agent? Adjudicating Unauthorized Behavior via Localizing Behavior-Guiding Instructions

evaluate Attnlocate across ten agent configurations from five LLM families, covering scenarios involving indirect prompt injection and tool poisoning. Attnlocate achieves a mean IoU of 0.743, an average AUROC

Beyond the Mandate: A Systematic Security Analysis of the Agent Payments Protocol (AP2)

messages and Model Context Protocol (MCP) tool calls. Prior work identified replay and prompt-injection attacks in AP2 v0.1. AP2 v0.2 addresses some of these issues but adds capabilities

Breakout/Interchange Reconnection as a driver of Jets, Fast CME, and Solar Energetic Particles

escape into interplanetary space. In situ measurements by PSP and Wind confirm the prompt injection of electron beams consistent with the timing of the explosive breakout reconnection. A fast shock

AgentFlow: A Flow-Centric Policy Language and Framework for Securing LLM Agent Systems

configured policies block the benchmark-specified policy-visible attacker flows; in ASB's direct-prompt-injection harness, attack success is 0/1{,}200. These results are preliminary and scoped

Xinference vulnerable to remote code execution via unsafe `eval()` in

CodeWhale versions >= 0.3.27 and < 0.8.64 (published as deepseek-tui >= 0.3.27

PACE: Policy-Attested Contract Execution for Safe AI Agents in Decentralized Finance

large language models (LLMs) to plan transactions, they inherit the LLM's susceptibility to prompt injection and lack of mechanisms to bind a verifier's approval to the exact transaction

Security of Foundation-Model-Powered Embodied Agents: Attack Surfaces, Attacks, Defenses, and Evaluation

inputs to physical behavior. Existing surveys often organize threats by mechanisms such as jailbreaks, prompt injection, backdoors, poisoning, or adversarial examples, but these categories do not consistently identify where

Agent-Native Telemetry: Verifiable State-Delta Evidence for Autonomous Operations

operations by 66.2%, detects all 500 tested adversarial storage mutations, and yields zero successful prompt injections across 50 adversarial trials per ATP configuration

Bounded Agents: Delegation Security for Multi-Agent AI Systems

prohibited outcome, or delegate authority to a sub-agent without limiting it. A prompt injection poses a risk only if the agent has authority to perform such actions; this

Rethinking Agent Security as a Networking Problem

driven behavior is inherently nondeterministic and vulnerable to manipulation through attacks such as prompt injection. As a result, current defenses cannot reliably prevent privacy and security threats, highlighting a critical

Stealing Reasoning Traces from Proprietary LLM APIs

safely rejects a malicious request. Fourth, attackers can leverage this flaw to execute invisible prompt injections, embedding malicious payloads entirely within encrypted blocks to poison public agentic rollouts. Following responsible

PromptShield Home: Ambient Multimodal Prompt Injection Defense for Smart-Home Agents

Smart-home assistants increasingly use multimodal large language models (MLLMs

LoginTrap: Uncovering Task-Agnostic Phishing-Style Indirect Prompt Injection Attacks against LLM-based Web Agents

LLM-based web agents automate user tasks by observing webpages

Open WebUI: Same-origin XSS to account takeover via terminal

Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent Skills

their capabilities as services while keeping the underlying packages hidden. Prior work focuses on prompt injection attacks that directly disclose these artifacts, and existing defenses accordingly aim to prevent such

Security of World-Model-Based Embodied AI: A Lifecycle of Threats, Defenses, and Evaluation

tools. We show that familiar attack families: poisoning, backdoors, adversarial examples, sensor spoofing, prompt injection, trajectory manipulation, and supply-chain attacks take on distinct meanings when they corrupt world states

@dynatrace-oss/dynatrace-mcp-server's create_dynatrace_notebook missing the human

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems

global risk context before irreversible actions are committed. Evaluated on four benchmarks spanning prompt injection, jailbreak-based unsafe tool use, risky code execution, and harmful web-agent behavior, SafeFlow reduces

Agentic Permissions Policy Algebra for Taint Confinement in LLM Agents

Autonomous LLM agents processing mixed-confidentiality data face severe security risks from prompt injection attacks and reasoning errors. While dynamic Information Flow Control (IFC) provides structural security guarantees, traditional taint